[Misc] Split model loader (#17712)

Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li
2025-05-07 12:42:26 +08:00
committed by GitHub
parent 8d84d836d1
commit 822de7fb94
21 changed files with 1681 additions and 1566 deletions
@@ -2,8 +2,7 @@
from vllm import SamplingParams
from vllm.config import LoadConfig, LoadFormat
from vllm.model_executor.model_loader.loader import (RunaiModelStreamerLoader,
get_model_loader)
from vllm.model_executor.model_loader import get_model_loader
test_model = "openai-community/gpt2"
@@ -24,7 +23,7 @@ def get_runai_model_loader():
def test_get_model_loader_with_runai_flag():
model_loader = get_runai_model_loader()
assert isinstance(model_loader, RunaiModelStreamerLoader)
assert model_loader.__class__.__name__ == "RunaiModelStreamerLoader"
def test_runai_model_loader_download_files(vllm_runner):
+1 -1
View File
@@ -10,7 +10,7 @@ import torch
from huggingface_hub import snapshot_download
from vllm import LLM, SamplingParams
from vllm.model_executor.model_loader.loader import ShardedStateLoader
from vllm.model_executor.model_loader import ShardedStateLoader
prompts = [
"Hello, my name is",
+1 -1
View File
@@ -29,7 +29,7 @@ from vllm.distributed import (ensure_model_parallel_initialized,
init_distributed_environment)
from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.entrypoints.openai.cli_args import make_arg_parser
from vllm.model_executor.model_loader.loader import get_model_loader
from vllm.model_executor.model_loader import get_model_loader
from vllm.platforms import current_platform
from vllm.transformers_utils.tokenizer import get_tokenizer
from vllm.utils import (FlexibleArgumentParser, GB_bytes,